manage_notifications

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are sparse (destructiveHint=false, title), so the description carries most of the burden; it does add that each action has a counterpart undo, and the enumerated verbs confirm non-destructive state toggles. However, 'the undo of each' overstates the enum: there is no 'read' to undo 'unread' and no 'archive' to undo 'unarchive', which could mislead an agent. It also omits any statement about required permissions or what state changes are applied.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single compact sentence with no filler, and the scoping constraint ('for one object') is front-loaded before the action list. The telegraphic style borders on cryptic but never wastes words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-required-parameter mutation tool with low schema coverage and no output schema, the description is too thin: it never clarifies the object identifier semantics, the workspace parameter, or that some undo actions are absent from the enum. It also gives no indication of the result of a call, leaving the agent to guess the return contract.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% — 'workspace' is undocumented and 'object' is described only as 'Issue id or object id', which is ambiguous about accepted id types. The description lists actions that merely restate the existing enum, adding no meaning, and says nothing about whether workspace is a slug or id. It does not compensate for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (notification inbox state on a single object) and enumerates the concrete operations (pin, hide, mark unread, unarchive, follow/unfollow), so the agent knows exactly what class of mutation this performs. 'For one object' usefully signals single-object scope, distinguishing it from list_notifications. The phrasing 'Inbox for one object' is a bit idiosyncratic but recoverable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance and no named alternative, despite siblings like list_notifications and mark_notifications_read that overlap in domain. The only hint is 'for one object', which weakly implies per-object scoping versus bulk operations. The agent must infer the routing decision from the tool name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.